China
Africa
Explore chapters and articles related to this topic
Image Processing Implementation for Medical Images to Detect and Classify Various Diseases on the Basis of MRI and Ultrasound Images
Published in Rashmi Gupta, Arun Kumar Rana, Sachin Dhawan, Korhan Cengiz, Advanced Sensing in Image Processing and IoT, 2022
Breast cancer is a form of cancer that originates in the breast. Figure 15.1 illustrates normal and cancerous breast tissue. When cells start to multiply out of control, then cancer begins. Breast cancer cells frequently form a tumor, which could be normally noticed on an X-ray or else felt like a lump [11]. Mostly it is women who suffer breast cancer, although males can also be affected.
A Review of Breast Cancer Detection Using Deep Learning Techniques
Published in Archana Mire, Vinayak Elangovan, Shailaja Patil, Advances in Deep Learning for Medical Image Analysis, 2022
Abhishek Das, Mihir Narayan Mohanty
Cancer tissue has two types of cancer cells, known as maturable and non-maturable. The tissue is composed of maturable types with few cells of non-maturable type. It has both genetic and environmental causes. Most cancers are initiated by malignant tumors. These tumors have rapid growth. Breast cancer is one of them. Non-invasive types of cancer are within the milk ducts. In this case, there is no growth or spread into any surrounding tissue. Invasive ductal carcinoma is a common type, comprising 80% of all breast cancers. Breast cancer is notified as the highest-incidence disease among all types of cancer according to the report provided in [1] in 2020. A graphic representation of this study is provided in Figure 5.1. The main reasons for breast cancer include obesity, ultraviolet radiation, and infections. Symptoms of breast cancer include development of a lump in the breast or armpit, dimpling of breast skin, swelling or thickness in any part of the breast, nipple bleeding or pain, and abnormal change in breast shape or size [2]. Early detection of breast cancer after such symptoms have been observed can prevent its development and also death.
Machine Learning Algorithms Used in Medical Field with a Case Study
Published in K. Gayathri Devi, Kishore Balasubramanian, Le Anh Ngoc, Machine Learning and Deep Learning Techniques for Medical Science, 2022
In investigative workup environment [14], DM has been made known to diminish the breast malignancy. In standard medical practice, mammograms are evaluated by the radiologists and Classification is done based on the American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) lexicon [15]. If any abnormality is detected in mammogram, a diagnostic workup that includes imaging modalities or additional mammographic views is typically required. Further evaluation using biopsy is recommended when lesion is suspicious. There are some risk factors which might raise the possibility of getting affected with breast cancer. Roughly about 80 percent of breast cancers are found in women neighboring the age of 50. Family history and Personal history may also raise the risk. Women who are with definite genetic mutations, as well as changes to the Breast Cancer (BRCA1 and BRCA2) genes, are at increased risk of having breast cancer during their life. Childbearing and menstrual history and other gene changes may also raise the risk. Due to the subtle difference between lesions and background fibro-glandular tissue, non-rigid nature of the breast and different lesion types, analysis of these images is difficult which leads to significant inter-observer and intra-observer variability [16].
GBDTMO: as new option for early-stage breast cancer detection and classification using machine learning
Published in Automatika, 2023
Vibith A. S., Jobin Christ M C
Breast cancer is examined and classified using a combination of techniques such as imaging, physical examination, and biopsy. Because of the disease’s complexity, early detection will improve patient survival. A dependable approach to diagnosis is required. Despite the use of numerous breast cancer datasets, disease prediction has become both interesting and difficult [3]. Machine learning methods greatly assist researchers in the field. However, many classification methods result in a poor diagnosis. Various case patterns are used to forecast the outcome of this case. The gradient boosting decision tree is a sophisticated ensemble model used for classification and regression. However, the method creates a poor prediction model in terms of speed and accuracy [4]. Furthermore, the boosting model constructs a sequential model, but the error rate is high. As a result, the need for a reliable approach remains a significant challenge [5]. With this inspiration, the paper includes the following contributions towards the accurate detection and classification of breast cancer.
Cell membrane-cloaked bioinspired nanoparticles: a novel strategy for breast cancer therapy
Published in Journal of Dispersion Science and Technology, 2023
Anuja Muley, Abhijeet Kulkarni, Prajakta Mahale, Vishal Gulecha
Radiation treatment, surgery, and anti-cancer drugs can all be used to treat breast cancer at the present. The lack of specificity in these therapies is a serious drawback. Increased biocompatibility, versatile encapsulation of active ingredients, decreased degradation during blood circulation, passive or active targeting, efficient delivery, and diminished or eliminated side effects are just a few of the potential advantages of nanoparticulate-based delivery systems. Doxil®, Abraxane®, and several more nanomedicines are in clinical trial and have been authorized by the US FDA [96–97]. Even so, the immune system classifies the foreign particle as "non-self" and will phagocytose it in order to kill it. The immune system will identify any nanosystem used to target tumors as foreign when it is administered. As a result, the nanosystem will have poor circulation and poor targeting. An innovative method of targeting tumors with cell membrane-coated nanoparticles has been developed to solve this issue. The nanoparticles are disguised by the cell membrane, which makes the immune system mistake the NPs for "self," leading to immunological deception and extended in vivo circulation [40, 98].
A prototype 3D modelling and visualisation pipeline for improved decision-making in breast reconstruction surgery
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2022
Sara Amini, Marta Kersten-Oertel
In 2020, more than 2 million new patients were diagnosed with breast cancer, making it the most common type of cancer in women (Sung, et al., 2021). Treatment options for breast cancer include: chemotherapy, radiotherapy, breast-conserving surgery and mastectomy. Mastectomy surgery, i.e. removal of breast tissue, is suggested for women who have a family history of breast cancer to avoid cancer (i.e. prophylactic mastectomy), patients who have recurrent cancer in the same breast, or in instances where breast-conserving surgery is not a possibility (DeSantis, et al., 2019). According to the National Cancer Database (NCDB, 2021), in 2018 more than 100,000 patients had a total mastectomy in the US alone. Many of these patients choose to have breast reconstruction surgery using an implant to restore the breast’s lost shape and volume. A breast implant is a silicone pocket filled with silicone gel or saline. There are a variety of implants available in different sizes and shapes, and typically the surgeon and the patient will agree on an implant to be used in a pre-surgery decision-making process.